Meshed-Memory Transformer for Image Captioning

Meshed-Memory Transformer

Abstract

Transformer-based architectures represent the state of the art in sequence modeling tasks like machine translation and language understanding. Their applicability to multi-modal contexts like image captioning, however, is still largely under-explored. With the aim of filling this gap, we present a Meshed Transformer with Memory for Image Captioning. The architecture improves both the image encoding and the language generation steps: it learns a multi-level representation of the relationships between image regions integrating learned a priori knowledge, and uses a mesh-like connectivity at decoding stage to exploit low-and high-level features. Experimentally, we investigate the performance of the M Transformer and different fully-attentive models in comparison with recurrent ones. When tested on COCO, our proposal achieves a new state of the art in single-model and ensemble configurations on the Karpathy test split and on the online test server. We also assess its performances when describing objects unseen in the training set.

Publication
IEEE/CVF Conference on Computer Vision and Pattern Recognition - CVPR 2020

Qualitative examples:

m2results

Results:

Meshed-Memory Transformer has been state-of-the-art model on the COCO test server Leaderboard for several months: COCOLeaderboard

Full Paper: pdf

Code: github

Please cite with the following BibTeX:

@article{cornia2019m,
  title={M $\^{} 2$: Meshed-Memory Transformer for Image Captioning},
  author={Cornia, Marcella and Stefanini, Matteo and Baraldi, Lorenzo and Cucchiara, Rita},
  journal={arXiv preprint arXiv:1912.08226},
  year={2019}
}
Matteo Stefanini
Matteo Stefanini
PhD in Artificial Intelligence | TEDx Organizer

I’m a (deep) learner who loves freedom. Working on Deep Learning, Genomics, Gene expression and Vision & Language. Driven to be useful for people.